Must-read papers on improving efficiency for pre-trained language models.

English | 中文说明 TextPruner是一个为预训练语言模型设计的模型裁剪工具包，通过轻量、快速的裁剪方法对模型进行结构化剪枝，从而实现压缩模型体积、提升模型速度。 其他相关资源： 知识蒸馏工具TextBrewer：https://github.com/airaria/TextBrewe

Structured Super Lottery Tickets in BERT This repo contains our codes for the paper "Super Tickets in Pre-Trained Language Models: From Model Compress

Top2Vec is an algorithm for topic modeling and semantic search. It automatically detects topics present in text and generates jointly embedded topic, document and word vectors.

Introduction This codebase contains source-code of the Python-based implementation (ARES) of our SIGIR 2022 paper. Chen, Jia, et al. "Axiomatically Re

Prompt-learning is the latest paradigm to adapt pre-trained language models (PLMs) to downstream NLP tasks, which modifies the input text with a textual template and directly uses PLMs to conduct pre

DART Implementation for ICLR2022 paper Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners. Environment